course: exclude auto-open from lesson_open telemetry, add session counts, filter synthetic sids

1 files changed, 6 insertions, 4 deletions

diff --git a/scripts/course-insights.py b/scripts/course-insights.py
index 0ee891e..299b264 100644
--- a/scripts/course-insights.py
+++ b/scripts/course-insights.py
@@ -14,21 +14,23 @@ def norm_q(q):
 
 def main():
     opens, completes, fails, cmds, questions = Counter(), Counter(), Counter(), Counter(), Counter()
-    projects = Counter()
+    projects = Counter(); sids = set()
     files = sorted(glob.glob(os.path.join(DATA, 'events-*.jsonl')))[-2:]
     for path in files:
         with open(path, encoding='utf-8', errors='ignore') as f:
             for line in f:
                 try: e = json.loads(line)
                 except Exception: continue
+                if (e.get('sid') or '').startswith('test'): continue
                 t, d = e.get('type'), e.get('detail') or {}
                 lesson = (d.get('lesson') or '')[:40]
-                if t == 'lesson_open' and lesson: opens[lesson] += 1
-                elif t == 'lesson_complete' and lesson: completes[lesson] += 1
+                if t == 'lesson_open' and lesson: opens[lesson] += 1; sids.add(e.get('sid') or '')
+                elif t == 'lesson_complete' and lesson: completes[lesson] += 1; sids.add(e.get('sid') or '')
                 elif t == 'exercise_fail':
                     if lesson: fails[lesson] += 1
                     c = (d.get('command') or '').strip().split(' ')[0][:40]
                     if c: cmds[c] += 1
+                    sids.add(e.get('sid') or '')
                 elif t == 'question':
                     q = norm_q(d.get('q'))
                     if len(q) >= 8: questions[q] += 1
@@ -46,7 +48,7 @@ def main():
                'top_failed_commands': [{'cmd': c, 'n': n} for c, n in cmds.most_common(20)],
                'top_questions': [{'q': q, 'n': n} for q, n in questions.most_common(20) if n >= 2],
                'projects': dict(projects),
-               'totals': {'opens': sum(opens.values()), 'completes': sum(completes.values()), 'failures': sum(fails.values())}}
+               'totals': {'sessions': len(sids), 'opens': sum(opens.values()), 'completes': sum(completes.values()), 'failures': sum(fails.values())}}
     os.makedirs(os.path.dirname(OUT), exist_ok=True)
     tmp = OUT + '.tmp'
     with open(tmp, 'w', encoding='utf-8') as f: json.dump(payload, f, ensure_ascii=False, indent=1)